Abstract
This paper presents the comparative analysis of various training algorithms based on artificial neural networks (ANNs) to compute space vector pulse width modulation (SVPWM) to control the switching pulses of an inverter. SVPWM has a high mathematical and computational complexity. ANN helps in minimization of this complex computation in SVPWM. This paper presents basic concepts behind different ANN algorithms, its comparative analysis for the application of computing SVPWM for a three-phase three-leg voltage-controlled inverter. Various Jacobian and gradient optimizers were used to train the ANN. Resultant network is tested on various parameters like mean squared errors (MSEs), time for training and total harmonic distortion (THD) of inverter.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
N. Langer, A.H. Bhat, P. Agarwal, Neural-network-based space-vector pulse-width modulation for capacitor voltage balancing of threephase three-level improved power quality converter. IET Power Electron. 7(4), 973–983 (2014)
N. Seth, V. Goel, R.D. Kulkami, Three phase innovative multilevel inverter topologies for research and industrial applications: a review, in 2017 International Conference on Nascent Technologies in Engineering (ICNTE), Navi Mumbai, pp. 1–6 (2017)
N. Seth, V. Goel, R.D. Kulkarni, V.P. Joshi, Performance analysis of seven level three phase asymmetric multilevel Inverter at various modulation indices, in 2016 International Conference on Electrical Power and Energy Systems (ICEPES), Bhopal, pp. 407–413 (2016)
Q.M. Attique, Y. Li, K. Wang, A survey on space-vector pulse width modulation for multilevel inverters. CPSS Trans. Power Electron. Appl. 2(3), 226–236 (2017). https://doi.org/10.24295/CPSSTPEA.2017.00021
D. Marquardt, An algorithm for least-squares estimation of nonlinear parameters. SIAM J. Appl. Math. 11(2), 431–441 (1963)
F. Rojas, R. Kennel, R. Cardenas, R. Repenning, J.C. Clare, M. Diaz, A new space-vector-modulation algorithm for a three-level four-leg NPC inverter. IEEE Trans. Energy Convers. 32(1), 23–35 (2017)
M. Riedmiller, H. Braun, A direct adaptive method for faster backpropagation learning: the RPROP algorithm, in IEEE International Conference on Neural Network, vol. 1, pp. 586–591 (1993)
J. Leonard, M.A. Kramer, Improvement of the backpropagation algorithm for training neural networks. Comput. Chem. Eng. 14, 337–341 (1990)
M.F. Møller, A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw. 6, 525–533 (1993)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Seth, N., Ubrani, A., Mane, S., Kazi, F.A.S. (2019). Comparative Analysis of Major Jacobian and Gradient Backpropagation Optimizers of ANN on SVPWM. In: Wang, J., Reddy, G., Prasad, V., Reddy, V. (eds) Soft Computing and Signal Processing . Advances in Intelligent Systems and Computing, vol 900. Springer, Singapore. https://doi.org/10.1007/978-981-13-3600-3_32
Download citation
DOI: https://doi.org/10.1007/978-981-13-3600-3_32
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-3599-0
Online ISBN: 978-981-13-3600-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)